"""
Demo is based on https://scikit-learn.org/stable/auto_examples/applications/plot_stock_market.html
"""

import sys
import numpy as np
import pandas as pd

symbol_dict = {
    "TOT": "Total",
    "XOM": "Exxon",
    "CVX": "Chevron",
    "COP": "ConocoPhillips",
    "VLO": "Valero Energy",
    "MSFT": "Microsoft",
    "IBM": "IBM",
    "TWX": "Time Warner",
    "CMCSA": "Comcast",
    "CVC": "Cablevision",
    "YHOO": "Yahoo",
    "DELL": "Dell",
    "HPQ": "HP",
    "AMZN": "Amazon",
    "TM": "Toyota",
    "CAJ": "Canon",
    "SNE": "Sony",
    "F": "Ford",
    "HMC": "Honda",
    "NAV": "Navistar",
    "NOC": "Northrop Grumman",
    "BA": "Boeing",
    "KO": "Coca Cola",
    "MMM": "3M",
    "MCD": "McDonald's",
    "PEP": "Pepsi",
    "K": "Kellogg",
    "UN": "Unilever",
    "MAR": "Marriott",
    "PG": "Procter Gamble",
    "CL": "Colgate-Palmolive",
    "GE": "General Electrics",
    "WFC": "Wells Fargo",
    "JPM": "JPMorgan Chase",
    "AIG": "AIG",
    "AXP": "American express",
    "BAC": "Bank of America",
    "GS": "Goldman Sachs",
    "AAPL": "Apple",
    "SAP": "SAP",
    "CSCO": "Cisco",
    "TXN": "Texas Instruments",
    "XRX": "Xerox",
    "WMT": "Wal-Mart",
    "HD": "Home Depot",
    "GSK": "GlaxoSmithKline",
    "PFE": "Pfizer",
    "SNY": "Sanofi-Aventis",
    "NVS": "Novartis",
    "KMB": "Kimberly-Clark",
    "R": "Ryder",
    "GD": "General Dynamics",
    "RTN": "Raytheon",
    "CVS": "CVS",
    "CAT": "Caterpillar",
    "DD": "DuPont de Nemours",
}


symbols, names = np.array(sorted(symbol_dict.items())).T

quotes = []

for symbol in symbols:
    print("Fetching quote history for %r" % symbol, file=sys.stderr)
    url = (
        "https://raw.githubusercontent.com/scikit-learn/examples-data/"
        "master/financial-data/{}.csv"
    )
    quotes.append(pd.read_csv(url.format(symbol)))

close_prices = np.vstack([q["close"] for q in quotes])
open_prices = np.vstack([q["open"] for q in quotes])

# The daily variations of the quotes are what carry the most information
variation = close_prices - open_prices


from sklearn import covariance

alphas = np.logspace(-1.5, 1, num=10)
edge_model = covariance.GraphicalLassoCV(alphas=alphas)

# standardize the time series: using correlations rather than covariance
# former is more efficient for structurerelations rather than covariance
# former is more efficient for structure recovery
X = variation.copy().T
X /= X.std(axis=0)
edge_model.fit(X)



from sklearn import cluster

_, labels = cluster.affinity_propagation(edge_model.covariance_, random_state=0)
n_labels = labels.max()



import gradio as gr

title = " 📈 Visualizing the stock market structure 📈"

with gr.Blocks(title=title) as demo:
    gr.Markdown(f"# {title}")
    gr.Markdown(" Data is of 56 stocks between the period of 2003 - 2008 <br>")
    gr.Markdown(" Stocks the move in together with each other are grouped together in a cluster <br>")

    gr.Markdown(" **[Demo is based on sklearn docs](https://scikit-learn.org/stable/auto_examples/applications/plot_stock_market.html)**")

    for i in range(n_labels + 1):
        gr.Markdown( f"Cluster {i + 1}: {', '.join(names[labels == i])}")
    
    gr.Markdown( f"## In progress")
demo.launch()